first commit

README.md

@@ -0,0 +1,26 @@
+### ANNOVAR
+This APP developed for the annotation of VCF files.
+
+**Please take care to check that the parameter `hg` is compatible with your reference genome reference builds version.**
+
+If the type and version of database currently used in the APP does not meet your needs, please contact the developer.
+### Getting Started
+
+We recommend using choppy system and Aliyun OSS service. The command will look like this:
+
+```
+# Activate the choppy environment
+$ open-choppy-env
+
+# Install the APP
+$ choppy install YaqingLiu/annovar [-f]
+
+# List the parameters
+$ choppy samples YaqingLiu/annovar-latest [--no-default]
+
+# Submit you task with the `samples.csv file` and `project name`
+$ choppy batch YaqingLiu/annovar-latest samples.csv -p Project [-l project:Label]
+
+# Query the status of all tasks in the project
+$ choppy query -L project:Label | grep "status"
+```

defaults

@@ -0,0 +1,7 @@
+{
+  "annovar_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/annovar:v2019.10",
+  "annovar_database": "oss://pgx-reference-data/annovar/",
+  "hg": "hg38",
+  "disk_size": "200",
+  "cluster_config": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc"
+}

inputs

@@ -0,0 +1,8 @@
+{
+  "{{ project_name }}.vcf": "{{ vcf }}",
+  "{{ project_name }}.annovar_docker": "{{ annovar_docker }}",
+  "{{ project_name }}.hg": "{{ hg }}",
+  "{{ project_name }}.annovar_database": "{{ annovar_database }}",
+  "{{ project_name }}.disk_size": "{{ disk_size }}",
+  "{{ project_name }}.cluster_config": "{{ cluster_config }}"
+}

tasks/annovar.wdl

@@ -0,0 +1,48 @@
+task annovar {
+
+  File vcf
+  String basename = basename(vcf,".vcf")
+  String hg
+  File annovar_database
+  String docker
+  String cluster_config
+  String disk_size
+
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+
+    if [ ${hg} == "hg38" ]; then
+    /installations/annovar/table_annovar.pl ${vcf}\
+    ${annovar_database} -buildver ${hg} \
+    -out ${basename} -remove \
+    -protocol rmsk \
+    -operation r \
+    -nastring . -vcfinput -thread $nt
+    fi
+
+    if [ ${hg} == "hg19" ]; then
+    /installations/annovar/table_annovar.pl ${vcf}\
+    ${annovar_database} -buildver ${hg} \
+    -out ${basename} -remove \
+    -protocol refGene,cytoBand,genomicSuperDups,ljb26_all,snp138,cosmic78,intervar_20170202,popfreq_all_20150413,clinvar_20190305 \
+    -operation g,r,r,f,f,f,f,f,f \
+    -nastring . -vcfinput -thread $nt
+    fi
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+
+  output {
+    File avinput = "${basename}.avinput"
+    File rmsk_txt = "${basename}.${hg}_rmsk.txt"
+    File rmsk_vcf = "${basename}.${hg}_rmsk.vcf"
+  }
+}

workflow.wdl

@@ -0,0 +1,21 @@
+import "./tasks/annovar.wdl" as annovar
+
+workflow {{ project_name }} {
+  
+  File vcf
+  String hg
+  File annovar_database
+  String annovar_docker
+  String disk_size
+  String cluster_config
+
+  call annovar.annovar as annovar {
+    input: 
+    vcf=vcf,
+    hg=hg,
+    annovar_database=annovar_database,
+    docker=annovar_docker,
+    cluster_config=cluster_config,
+    disk_size=disk_size
+  }
+}